# HELP llamacpp:prompt_tokens_total Number of prompt tokens processed.
# TYPE llamacpp:prompt_tokens_total counter
llamacpp:prompt_tokens_total 4096
# HELP llamacpp:prompt_seconds_total Prompt process time
# TYPE llamacpp:prompt_seconds_total counter
llamacpp:prompt_seconds_total 3
# HELP llamacpp:tokens_predicted_total Number of generation tokens processed.
# TYPE llamacpp:tokens_predicted_total counter
llamacpp:tokens_predicted_total 2560
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
# TYPE llamacpp:tokens_predicted_seconds_total counter
llamacpp:tokens_predicted_seconds_total 21
# HELP llamacpp:n_decode_total Total number of llama_decode() calls
# TYPE llamacpp:n_decode_total counter
llamacpp:n_decode_total 1024
# HELP llamacpp:n_tokens_max Largest observed n_tokens.
# TYPE llamacpp:n_tokens_max counter
llamacpp:n_tokens_max 4224
# HELP llamacpp:spec_decode_num_draft_tokens_total Total draft tokens generated
# TYPE llamacpp:spec_decode_num_draft_tokens_total counter
llamacpp:spec_decode_num_draft_tokens_total 0
# HELP llamacpp:spec_decode_num_accepted_tokens_total Total draft tokens accepted by the target model
# TYPE llamacpp:spec_decode_num_accepted_tokens_total counter
llamacpp:spec_decode_num_accepted_tokens_total 0
# HELP llamacpp:spec_decode_num_drafts_total Total speculative decoding verification steps
# TYPE llamacpp:spec_decode_num_drafts_total counter
llamacpp:spec_decode_num_drafts_total 0
# HELP llamacpp:prompt_tokens_seconds Average prompt throughput in tokens/s.
# TYPE llamacpp:prompt_tokens_seconds gauge
llamacpp:prompt_tokens_seconds 1365.3333
# HELP llamacpp:predicted_tokens_seconds Average generation throughput in tokens/s.
# TYPE llamacpp:predicted_tokens_seconds gauge
llamacpp:predicted_tokens_seconds 121.9047
# HELP llamacpp:requests_processing Number of requests processing.
# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
# HELP llamacpp:requests_deferred Number of requests deferred.
# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0
# HELP llamacpp:n_busy_slots_per_decode Average number of busy slots per llama_decode() call
# TYPE llamacpp:n_busy_slots_per_decode gauge
llamacpp:n_busy_slots_per_decode 0.5
